SIMARDEEP KAUR
[ adc38k@r.postjobfree.com Ó +1-236-***-**** Vancouver, BC linkedin.com/in/simar0510 github.com/SimardeepKaur SKILLS
Python R SQL Scikit-Learn
Pandas Matplotlib TensorFlow
Map Reduce Power BI NLP
Algorithms and Data Structures
Git and Version control Data cleaning
Statistical modeling Data Visualization
Problem-solving and critical thinking
Predictive Modeling PostgreSQL
Web Scraping Feature Selection
EDUCATION
M.Sc. in Data Science Candidate
University of British Columbia
Sept 2019 – Present
B.E. in Electrical Engineering
Thapar University
Aug 2014 – July 2018
CERTIFICATIONS
Machine Learning by Stanford University [Jan
2019]
The Data Scientist’s Tool-box by John Hopkins
University (JHU) [Dec 2018]
R Programming by JHU [Dec 2018]
Getting and cleaning data by JHU [Dec 2018]
Exploratory Data Analysis by JHU [Dec 2018]
Reproducible Research by JHU [Dec 2018]
MOST PROUD OF
3
Thapar University Merit
Scholarship(2014- 2016)
Recipient of Scholarship for being in
top 10% of the electrical department
3
Overall Discipline Coordinator(2015-
2017)
Selected to manage and lead the ad-
mission counselling society at Thapar
University, Froshweek
z
Mathematics Tutor(2015- 2017)
Volunteered two hours per week to
help students understand concepts,
solve problems, and prepare for tests
in “Pratigya” Society at Thapar Univer-
sity
EXPERIENCE
Business Technology Analyst
Deloitte Consulting India Pvt. Ltd
Aug 2018 – Aug 2019 Bangalore, India
Extracting and cleansing the data from SAP systems using ETL tools like Tal- end/Informatica by writing complex SQL statements and stored procedures
Reduced around 80 % manual efforts by automating accounting/ledger bal- ance data load using DellBoomi
Applied native NetSuite APIs to optimize script customizations associated with invoicing processes
Data Analytics Intern
Concept International Business Consulting
Jan 2018 – Jun 2018 Gurgaon, India
Assisted in advocating game plans for potential investors using data visual- izations
Intensive cleaning and wrangling of data collected from industries of differ- ent domains
Implemented predictive analytic techniques to develop a strategy to enter Indian market
PROJECTS
Search Optimization NNCL, Thapar University
Jan 2018 – July 2018 Thapar University
Use of NLP pipeline and ISBN indexing to issue tags using descriptor similar- ity between books
Developed word2vec models for stochastic predictions
Achieved the correlation between the predicted word and user required ac- tual word of 0.84
NFL predictor
Jan 2020 – Feb 2020 UBC
Used classification techniques like Random forest and logistic regression to achieve an accuracy of 75% to predict the results using ELO rating
Built an automated data analysis pipeline using an automation tool, Make to combine the scripts for loading, cleaning,analyzing and visualizing data
Used Docker to make the project reproducible on any machine Job Analyzer App
Nov 2019 – Dec 2019 UBC
Collaborated with a team of 3 people to develop an app to show the chang- ing job trends
Data manipulation using pandas and tidyverse
Developed interactive data visualizations using both Python and R imple- mentation of dash
Air quality Index prediction
Nov 2019 – Dec 2019 Vancouver
Improved accuracy of Xgboost Regression upto 50% using hyperparameter optimiziation and predictive modeling techniques
Collected raw data using web scraping and cleaned it using pandas